Scaffold Dashboard logo

Scaffold Dashboard

Community
ahpxex
scaffold-dashboard

Stand up the dashboard foundation (the platform layer — UI primitives, form system, charts, Repository + adapters, auth seam, theme, routing shell) into a new project as a zero-config runnable app. Run this FIRST when building a dashboard, then compose screens from the add-component catalogue's shapes (add-detail-page, add-kanban, …) and the add-backend operation skill.

Overview

Publisherahpxex
Repositoryopen-dashboard
Skill namescaffold-dashboard
Stars
148
Forks
13
Bundled files
149
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 149 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by ahpxex on GitHub. Read the source before you install it.

Installation

Install the Scaffold Dashboard AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/ahpxex/open-dashboard/tree/main/.claude/skills/scaffold-dashboard
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/ahpxex/open-dashboard.git /tmp/open-dashboard
mkdir -p .claude/skills
cp -r /tmp/open-dashboard/.claude/skills/scaffold-dashboard .claude/skills/scaffold-dashboard
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Scaffold Dashboard in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Scaffold Dashboard on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Scaffold Dashboard is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Scaffold the dashboard foundation

The whole foundation is bundled at base/ — a clean, runnable app shell with no demo content. Materialize it into a new project, then add screens from the add-component catalogue's shapes (and the add-backend operation skill). You don't read the foundation code — you scaffold it.

Scaffold

bash
bash .claude/skills/scaffold-dashboard/scaffold.sh <target-dir>

Copies base/ → target and runs bun install. Then:

bash
cd <target-dir>
bun run dev          # zero-config: in-memory auth + data, no Postgres/Docker

Open it, click Dev quick login (dev@example.com / password) → an empty, branded dashboard.

What you get

TanStack Start + Router + Query + Table; shadcn-on-@base-ui/react primitives; Tailwind v4 theme; the form system (TanStack Form + zod); chart components; the Repository data layer (in-memory by default, Drizzle/Postgres when DATABASE_URL is set); better-auth behind the AuthProvider seam; toast + useConfirm; and the auth-guarded routing shell. Rebrand via src/config/app.ts (or the rebrand skill).

Compose a coherent product (not a demo dump)

You are building a real back-office for a specific domain — not showcasing the catalogue. The fastest way to ship something that reads as a patchwork demo is to copy a pile of gallery shapes into the nav. Don't. Instead:

  • The home is an overview, never the placeholder. Replace src/routes/_app/index.tsx (the "clean shell" welcome) with a real overview via add-chart-page — KPIs + charts derived from your actual resources. Shipping the scaffold welcome as the product home is the #1 tell of a demo.
  • Nav = real product sections only: Overview, your resources, Settings. The scaffold base ships clean (no demo resources, no Skills Gallery) — you add product sections to src/lib/sidebar-items.ts, you don't prune sample ones.
  • Pick the archetype that fits each resource's shape, don't add one of each: flat list → CRUD table (add-backend); rich record → + add-detail-page; an inbox you triage → add-master-detail; a staged pipeline → add-kanban; people/visual items → add-card-list; date-bound items → add-calendar; metrics → add-chart-page.
  • Every nav item gets a distinct, meaningful Phosphor icon — never repeat one icon (e.g. SquaresFourIcon) down the list.
  • Use product language. Labels and page copy name the domain, not the mechanism: "Feed", not "Feed (REST)"; "Manage your invoices", not "Generated resource — customise the schema".
  • Seed believable data — real names, dates, statuses, amounts. Three rows of Alpha/Beta/Gamma read as a demo; a dozen realistic records read as a product.

Add screens (compose from the add-component catalogue)

The shapes below are references inside the single add-component catalogue (not separate invocable skills); each copies a bundled template into the new project. Data + CRUD comes from the add-backend operation skill.

  • Resources (data + CRUD): bun run create-resource <name> (or add-backend), then the catalogue's add-detail-page, add-master-detail, add-card-list, add-form, add-chart-page.
  • Shapes (all in add-component): add-list-view, add-kanban, add-tree-view, add-calendar, add-timeline, add-virtual-table, add-inline-edit, add-filter-panel, add-wizard-form, add-field-combobox, add-record-tabs, add-settings-page, add-empty-state, add-page-layout, add-data-display, add-feedback-states.

After copying a template, add a sidebar entry in src/lib/sidebar-items.ts (above the // create-resource:anchor) so it shows in the nav.

Verify

bash
cd <target-dir>
bun run typecheck && bun run check && bun run test && bun run build

All green on the empty shell (and after each screen you add). bun run dev boots zero-config.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

and 89 more files.

Frequently asked questions

What does the Scaffold Dashboard AI skill do?

Stand up the dashboard foundation (the platform layer — UI primitives, form system, charts, Repository + adapters, auth seam, theme, routing shell) into a new project as a zero-config runnable app. Run this FIRST when building a dashboard, then compose screens from the add-component catalogue's shapes (add-detail-page, add-kanban, …) and the add-backend operation skill.

Why use Scaffold Dashboard on TypingMind?

Because you install it once and use it with any model. Scaffold Dashboard is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Scaffold Dashboard in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/ahpxex/open-dashboard/tree/main/.claude/skills/scaffold-dashboard. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Scaffold Dashboard?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Scaffold Dashboard?

As many as you like. As long as a model supports skills, you can use Scaffold Dashboard with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Scaffold Dashboard AI skill free?

Yes. It is published on GitHub by ahpxex under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇